© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23393
    Prev
    Next
    INDEX
    Explanations

    antenna, RF, power

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    拇
    0.39
     बचेगा
    0.37
     opin
    0.37
     blisters
    0.37
    RESOURCE
    0.36
     agit
    0.35
     shr
    0.35
    ඟ
    0.34
     náz
    0.34
     macer
    0.34
    POSITIVE LOGITS
     bog
    0.52
    bog
    0.48
     Patch
    0.48
     me
    0.46
     Bog
    0.45
     patch
    0.45
    Bog
    0.44
    Dip
    0.43
    Patch
    0.41
     patches
    0.41
    Activations Density 0.024%

    No Known Activations